setwd("~/Documents/GitHub/Resultados/docs/PrimeroDiffExpAllResults/Clasificando/Abundances")
load('CheackPointOne.RData')

Segunda Clasificacion: pEhExvsCmasM

head(pEhExvsCmasM,10);
##          GenId    CDC5_1     CDC5_2    CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1  EHI_000130A  45.32378  107.82734 128.66351  180.07428  446.15729  516.14317
## 2  EHI_000140A  66.04322  317.74653 257.32703  363.20067  351.59134   41.84945
## 3  EHI_000240A 700.57610 1282.45711 877.45524 1208.63415 1993.15918 2290.09468
## 4  EHI_000250A 707.05093  430.16227 388.98271  334.20566  337.04273  710.66559
## 5  EHI_000260A  94.53245  108.97444  35.15805  112.16491   69.10588   54.24928
## 6  EHI_000280A  58.27343   50.47237  80.78872   56.46397   86.07926   66.64912
## 7  EHI_000290A  27.19427   14.91229  23.93740   19.07567   14.54861   87.57384
## 8  EHI_000300A  60.86336  143.38742 110.71046  137.34479  118.81363   34.09955
## 9  EHI_000410A  15.53958   21.79489  23.18935   28.99501   25.46006   70.52407
## 10 EHI_000430A  27.19427   27.53039  22.44131   26.70593   14.54861   11.62485
nbreaks <- 10
data2 <- pEhExvsCmasM;       head(data2)
##         GenId    CDC5_1     CDC5_2    CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  45.32378  107.82734 128.66351  180.07428  446.15729  516.14317
## 2 EHI_000140A  66.04322  317.74653 257.32703  363.20067  351.59134   41.84945
## 3 EHI_000240A 700.57610 1282.45711 877.45524 1208.63415 1993.15918 2290.09468
## 4 EHI_000250A 707.05093  430.16227 388.98271  334.20566  337.04273  710.66559
## 5 EHI_000260A  94.53245  108.97444  35.15805  112.16491   69.10588   54.24928
## 6 EHI_000280A  58.27343   50.47237  80.78872   56.46397   86.07926   66.64912

Log-Normalización

sample1   <- data2$pEhEx_1; sample2   <- data2$pEhEx_2; sample3   <- data2$pEhEx_3;
samplevs1 <- data2$CDC5_1;  samplevs2 <- data2$CDC5_2;  samplevs3 <- data2$CDC5_3;
log2sample1 <- log2(sample1+1);         log2sample2 <- log2(sample2+1)
log2sample3 <- log2(sample3+1);         log2samplevsCDC51 <- log2(samplevs1+1)
log2samplevsCDC52 <- log2(samplevs2+1); log2samplevsCDC53 <- log2(samplevs3+1)
data2 <- cbind(data2, log2sample1,log2sample2,log2sample3,
               log2samplevsCDC51,log2samplevsCDC52,log2samplevsCDC53)
head(data2)
##         GenId    CDC5_1     CDC5_2    CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  45.32378  107.82734 128.66351  180.07428  446.15729  516.14317
## 2 EHI_000140A  66.04322  317.74653 257.32703  363.20067  351.59134   41.84945
## 3 EHI_000240A 700.57610 1282.45711 877.45524 1208.63415 1993.15918 2290.09468
## 4 EHI_000250A 707.05093  430.16227 388.98271  334.20566  337.04273  710.66559
## 5 EHI_000260A  94.53245  108.97444  35.15805  112.16491   69.10588   54.24928
## 6 EHI_000280A  58.27343   50.47237  80.78872   56.46397   86.07926   66.64912
##   log2sample1 log2sample2 log2sample3 log2samplevsCDC51 log2samplevsCDC52
## 1    7.500438    8.804639    9.014420          5.533681          6.765897
## 2    8.508590    8.461853    5.421205          6.067020          8.316266
## 3   10.240355   10.961565   11.161821          9.454456         10.325819
## 4    8.388903    8.401062    9.475056          9.467709          8.752087
## 5    6.822283    6.131464    5.787884          6.577919          6.781024
## 6    5.844586    6.444257    6.079999          5.889314          5.685726
##   log2samplevsCDC53
## 1          7.018629
## 2          8.013055
## 3          9.778825
## 4          8.607266
## 5          5.176245
## 6          6.353830
save.image('CheckPointThree.RData')
setwd("~/Documents/GitHub/Resultados/docs/PrimeroDiffExpAllResults/Clasificando/Abundances")
#load('CheckPointTwo.RData')
library(ggplot2);library(dplyr);library("fitdistrplus");
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
## Loading required package: MASS
## 
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
## 
##     select
## Loading required package: survival
library("MASS");library("survival")
head(data2)
##         GenId    CDC5_1     CDC5_2    CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  45.32378  107.82734 128.66351  180.07428  446.15729  516.14317
## 2 EHI_000140A  66.04322  317.74653 257.32703  363.20067  351.59134   41.84945
## 3 EHI_000240A 700.57610 1282.45711 877.45524 1208.63415 1993.15918 2290.09468
## 4 EHI_000250A 707.05093  430.16227 388.98271  334.20566  337.04273  710.66559
## 5 EHI_000260A  94.53245  108.97444  35.15805  112.16491   69.10588   54.24928
## 6 EHI_000280A  58.27343   50.47237  80.78872   56.46397   86.07926   66.64912
##   log2sample1 log2sample2 log2sample3 log2samplevsCDC51 log2samplevsCDC52
## 1    7.500438    8.804639    9.014420          5.533681          6.765897
## 2    8.508590    8.461853    5.421205          6.067020          8.316266
## 3   10.240355   10.961565   11.161821          9.454456         10.325819
## 4    8.388903    8.401062    9.475056          9.467709          8.752087
## 5    6.822283    6.131464    5.787884          6.577919          6.781024
## 6    5.844586    6.444257    6.079999          5.889314          5.685726
##   log2samplevsCDC53
## 1          7.018629
## 2          8.013055
## 3          9.778825
## 4          8.607266
## 5          5.176245
## 6          6.353830

Muestra 1

log2sample1 <- data2$log2sample1; head(mean(log2sample1)); head(sd(log2sample1))
## [1] 6.460339
## [1] 2.834041
head(log2sample1,5)
## [1]  7.500438  8.508590 10.240355  8.388903  6.822283
summary(data2)
##     GenId               CDC5_1             CDC5_2              CDC5_3        
##  Length:4691        Min.   :     0.0   Min.   :     0.00   Min.   :     0.0  
##  Class :character   1st Qu.:    19.4   1st Qu.:    19.50   1st Qu.:    20.9  
##  Mode  :character   Median :    50.5   Median :    56.21   Median :    54.6  
##                     Mean   :  1930.9   Mean   :  1790.28   Mean   :  2024.1  
##                     3rd Qu.:   209.8   3rd Qu.:   248.92   3rd Qu.:   223.3  
##                     Max.   :405707.4   Max.   :282737.06   Max.   :384267.8  
##     pEhEx_1             pEhEx_2             pEhEx_3          log2sample1    
##  Min.   :     0.00   Min.   :     0.00   Min.   :     0.0   Min.   : 0.000  
##  1st Qu.:    19.84   1st Qu.:    18.19   1st Qu.:    17.0   1st Qu.: 4.381  
##  Median :    55.70   Median :    56.98   Median :    60.4   Median : 5.825  
##  Mean   :  1503.81   Mean   :  1895.10   Mean   :  2146.4   Mean   : 6.460  
##  3rd Qu.:   227.38   3rd Qu.:   250.96   3rd Qu.:   272.4   3rd Qu.: 7.835  
##  Max.   :219640.26   Max.   :288237.01   Max.   :781911.9   Max.   :17.745  
##   log2sample2      log2sample3     log2samplevsCDC51 log2samplevsCDC52
##  Min.   : 0.000   Min.   : 0.000   Min.   : 0.000    Min.   : 0.000   
##  1st Qu.: 4.262   1st Qu.: 4.174   1st Qu.: 4.352    1st Qu.: 4.358   
##  Median : 5.858   Median : 5.941   Median : 5.687    Median : 5.838   
##  Mean   : 6.424   Mean   : 6.345   Mean   : 6.361    Mean   : 6.456   
##  3rd Qu.: 7.977   3rd Qu.: 8.095   3rd Qu.: 7.720    3rd Qu.: 7.965   
##  Max.   :18.137   Max.   :19.577   Max.   :18.630    Max.   :18.109   
##  log2samplevsCDC53
##  Min.   : 0.000   
##  1st Qu.: 4.456   
##  Median : 5.797   
##  Mean   : 6.531   
##  3rd Qu.: 7.809   
##  Max.   :18.552
ndata2    <- length(log2sample1)
hist(log2sample1, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample1')

meanlog2sample1 <- mean(log2sample1); head(meanlog2sample1)
## [1] 6.460339
StdDevlog2sample1 <- sd(log2sample1); head(StdDevlog2sample1)
## [1] 2.834041
Normlog2sample1 <- (log2sample1-meanlog2sample1)/StdDevlog2sample1; head(Normlog2sample1)
## [1]  0.3670021  0.7227316  1.3337904  0.6804997  0.1277131 -0.2172704
tst<- Normlog2sample1

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 3.118970e-17 0.01459893
## sd   9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293

Cálculo de cuantiles

CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8599158 0.8169091
## 70 -0.9371527 0.9617338
## 75 -0.9960331 1.1293972
## 80 -1.0282412 1.3839029
## 85 -1.0995019 1.7041875
## 90 -1.1392596 2.1899810
## 95 -1.2814439 2.6187913
## 99 -1.6734604 3.1869302
col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED', lty=9)
abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra 2

log2sample2 <- data2$log2sample2; head(mean(log2sample2)); head(sd(log2sample2))
## [1] 6.424318
## [1] 3.078114
head(log2sample2,5)
## [1]  8.804639  8.461853 10.961565  8.401062  6.131464
ndata2    <- length(log2sample2)
hist(log2sample2, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample2')

Log-normalizacion

meanlog2sample2 <- mean(log2sample2); head(meanlog2sample2)
## [1] 6.424318
StdDevlog2sample2 <- sd(log2sample2); head(StdDevlog2sample2)
## [1] 3.078114
Normlog2sample2 <- (log2sample2-meanlog2sample2)/StdDevlog2sample2; head(Normlog2sample2)
## [1]  0.773304903  0.661942766  1.474034750  0.642193202 -0.095140848
## [6]  0.006477743
tst<- Normlog2sample2
hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajuste de modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -7.845328e-17 0.01459893
## sd    9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]

print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8804743 0.8477586
## 70 -0.9259047 0.9845324
## 75 -0.9762161 1.1416416
## 80 -1.0325848 1.3729846
## 85 -1.1709305 1.7147626
## 90 -1.2592113 2.1352442
## 95 -1.5101169 2.5267006
## 99 -2.0870956 3.0982665
col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA (sample 2)', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra 3

log2sample3 <- data2$log2sample3; head(mean(log2sample3)); head(sd(log2sample3))
## [1] 6.345251
## [1] 3.202711
head(log2sample3,5)
## [1]  9.014420  5.421205 11.161821  9.475056  5.787884
ndata2    <- length(log2sample3)
hist(log2sample3, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample2')

meanlog2sample3 <- mean(log2sample3); head(meanlog2sample3)
## [1] 6.345251
StdDevlog2sample3 <- sd(log2sample3); head(StdDevlog2sample3)
## [1] 3.202711
Normlog2sample3 <- (log2sample3-meanlog2sample3)/StdDevlog2sample3; head(Normlog2sample3)
## [1]  0.83340927 -0.28851998  1.50390416  0.97723608 -0.17402974 -0.08282095
tst<- Normlog2sample3
hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando Modelos

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 2.404120e-17 0.01459893
## sd   9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##              mean           sd
## mean 1.000000e+00 1.713307e-11
## sd   1.713307e-11 1.000000e+00
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8675316 0.8402759
## 70 -0.9659157 0.9685687
## 75 -1.0459211 1.1104543
## 80 -1.1432722 1.3204414
## 85 -1.2676335 1.6079001
## 90 -1.4400018 1.9997962
## 95 -1.7227405 2.4584046
## 99 -1.9812123 3.0490511

Creación de histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA (sample 3)', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA (sample 3)', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC51

log2vsCDC51 <- data2$log2samplevsCDC51; head(mean(log2vsCDC51)); head(sd(log2vsCDC51))
## [1] 6.360533
## [1] 2.885557
head(log2vsCDC51,5)
## [1] 5.533681 6.067020 9.454456 9.467709 6.577919
ndata2    <- length(log2vsCDC51)
hist(log2vsCDC51, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC51')

meanlog2vsCDC51 <- mean(log2vsCDC51); head(meanlog2vsCDC51)
## [1] 6.360533
StdDevlog2vsCDC51 <- sd(log2vsCDC51); head(StdDevlog2vsCDC51)
## [1] 2.885557
Normlog2vsCDC51 <- (log2vsCDC51-meanlog2vsCDC51)/StdDevlog2vsCDC51; head(Normlog2vsCDC51)
## [1] -0.28654857 -0.10171821  1.07220996  1.07680301  0.07533583 -0.16330282
tst<- Normlog2vsCDC51

Primer histograma

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC51',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 4.727431e-17 0.01459893
## sd   9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##              mean           sd
## mean 1.000000e+00 3.426614e-11
## sd   3.426614e-11 1.000000e+00
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8422310 0.8070408
## 70 -0.8866144 0.9258394
## 75 -0.9353250 1.1082535
## 80 -0.9892988 1.3411647
## 85 -1.0498123 1.6503084
## 90 -1.1186718 2.1232202
## 95 -1.2936703 2.7259168
## 99 -2.2042655 3.3471237

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC51 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC52

log2vsCDC52 <- data2$log2samplevsCDC52; head(mean(log2vsCDC52)); head(sd(log2vsCDC52))
## [1] 6.456006
## [1] 2.961412
head(log2vsCDC52,5)
## [1]  6.765897  8.316266 10.325819  8.752087  6.781024

Primer Histograma

ndata2    <- length(log2vsCDC52)
hist(log2vsCDC52, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC52')

meanlog2vsCDC52 <- mean(log2vsCDC52); head(meanlog2vsCDC52)
## [1] 6.456006
StdDevlog2vsCDC52 <- sd(log2vsCDC52); head(StdDevlog2vsCDC52)
## [1] 2.961412
Normlog2vsCDC52 <- (log2vsCDC52-meanlog2vsCDC52)/StdDevlog2vsCDC52; head(Normlog2vsCDC52)
## [1]  0.1046430  0.6281664  1.3067458  0.7753331  0.1097511 -0.2601055
tst<- Normlog2vsCDC52

** Segundo Histograma**

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC52',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -1.572806e-17 0.01459893
## sd    9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

Cálculo de cuantiles

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8684632 0.8127421
## 70 -0.9078618 0.9668311
## 75 -0.9977360 1.1263553
## 80 -1.0497676 1.3726202
## 85 -1.1080283 1.6925494
## 90 -1.1742151 2.1332703
## 95 -1.3417825 2.5710200
## 99 -2.1800429 3.1603637

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC52 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC53

log2vsCDC53 <- data2$log2samplevsCDC53; head(mean(log2vsCDC53)); head(sd(log2vsCDC53))
## [1] 6.53086
## [1] 2.83016
head(log2vsCDC53,5)
## [1] 7.018629 8.013055 9.778825 8.607266 5.176245
ndata2    <- length(log2vsCDC53)

** Primer histograma**

hist(log2vsCDC53, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC53')

meanlog2vsCDC53 <- mean(log2vsCDC53); head(meanlog2vsCDC53)
## [1] 6.53086
StdDevlog2vsCDC53 <- sd(log2vsCDC53); head(StdDevlog2vsCDC53)
## [1] 2.83016
Normlog2vsCDC53 <- (log2vsCDC53-meanlog2vsCDC53)/StdDevlog2vsCDC53; head(Normlog2vsCDC53)
## [1]  0.17234655  0.52371392  1.14762562  0.73367078 -0.47863552 -0.06255138
tst<- Normlog2vsCDC53

Segundo histograma

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC53',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 4.356074e-17 0.01459893
## sd   9.998934e-01 0.01032296
## Loglikelihood:  -6655.741   AIC:  13315.48   BIC:  13328.39 
## Correlation matrix:
##               mean            sd
## mean  1.000000e+00 -3.426614e-11
## sd   -3.426614e-11  1.000000e+00
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

Calculo de cuantiles

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8498210 0.8013314
## 70 -0.8954944 0.9236834
## 75 -0.9456663 1.1144463
## 80 -1.0013208 1.3533967
## 85 -1.0316061 1.7113380
## 90 -1.0981755 2.2519051
## 95 -1.2178539 2.7028284
## 99 -1.5625210 3.3998336

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC53 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))